Are sparse representations really relevant for image classification?

Authors:
R. Rigamonti;M. A. Brown;V. Lepetit
Affiliations:
CVLab, EPFL, Lausanne, Switzerland;CVLab, EPFL, Lausanne, Switzerland;CVLab, EPFL, Lausanne, Switzerland
Venue:
CVPR '11 Proceedings of the 2011 IEEE Conference on Computer Vision and Pattern Recognition
Year:
2011

Citing 0
Cited 8

Supervised sparse representation method with a heuristic strategy and face recognition experiments

Neurocomputing
Heteroscedastic Sparse Representation Based Classification for Face Recognition

Neural Processing Letters
Accurate and efficient linear structure segmentation by leveraging ad hoc features with learned filters

MICCAI'12 Proceedings of the 15th international conference on Medical Image Computing and Computer-Assisted Intervention - Volume Part I
Sparse representation and learning in visual recognition: Theory and applications

Signal Processing
Sparse coding based visual tracking: Review and experimental comparison

Pattern Recognition
Manifold based sparse representation for facial understanding in natural images

Image and Vision Computing
A novel ensemble algorithm for tumor classification

ISNN'13 Proceedings of the 10th international conference on Advances in Neural Networks - Volume Part II
Letters: Two-dimensional relaxed representation

Neurocomputing

Quantified Score

Hi-index	0.00

Visualization

Abstract

Recent years have seen an increasing interest in sparse representations for image classification and object recognition, probably motivated by evidence from the analysis of the primate visual cortex. It is still unclear, however, whether or not sparsity helps classification. In this paper we evaluate its impact on the recognition rate using a shallow modular architecture, adopting both standard filter banks and filter banks learned in an unsupervised way. In our experiments on the CIFAR-10 and on the Caltech-101 datasets, enforcing sparsity constraints actually does not improve recognition performance. This has an important practical impact in image descriptor design, as enforcing these constraints can have a heavy computational cost.